CBS - Post doc in Metabolomics for Health Applications

Position Overview:

We are seeking a highly qualified Postdoctoral Researcher to join its multidisciplinary research team working at the intersection of Artificial Intelligence (AI), Metabolomics, and Precision Health. The project aims to leverage AI and machine learning (ML) to analyze complex metabolomics datasets and address key health challenges, including biomarker discovery, disease classification, patient stratification, and personalized therapeutic strategies.

The successful candidate will contribute to high-impact research projects focusing on metabolic diseases, cancer, neurodegenerative disorders, and microbiome-related health issues by applying advanced AI/ML techniques for biomarker discovery and metabolic network modeling.

Scientific Challenges Addressed in the Position:

• High-dimensionality and complexity of metabolomics data, requiring advanced AI/ML techniques for robust analysis and interpretation.
• Integration of multi-omics data (genomics, transcriptomics, proteomics, and metabolomics) to achieve systems-level insights into disease mechanisms.
• Identification and validation of clinically relevant metabolic biomarkers for early disease detection, prognosis, and treatment response monitoring.
• Reconstruction of metabolic networks and pathway analysis to understand disease-specific metabolic reprogramming.
• Tackling data sparsity, batch effects, and heterogeneity in clinical metabolomics datasets.
• Developing explainable AI (XAI) models to facilitate clinical decision support systems (CDSS) and enhance trustworthiness in healthcare settings.
• Addressing longitudinal and time-series data analysis for monitoring disease progression and treatment outcomes.

Key Responsibilities:

• Develop and implement AI/ML pipelines for feature selection, dimensionality reduction, and predictive modeling using metabolomics data from clinical studies.
• Apply deep learning models (e.g., autoencoders, variational autoencoders, graph neural networks) for biomarker discovery, disease classification, and patient stratification.
• Integrate multi-omics datasets to identify metabolic signatures and elucidate pathway-level alterations associated with disease phenotypes.
• Perform network-based analysis and reconstruction of metabolic pathways to uncover functional mechanisms underlying health and disease.
• Contribute to the development of personalized medicine strategies, including precision diagnostics and predictive models for treatment response.
• Collaborate with experimental teams, clinicians, and biostatisticians to validate computational findings in clinical cohorts.
• Publish research findings in peer-reviewed journals and present at international conferences.
• Mentor graduate students and contribute to building capacity in AI and health data science at UM6P.

Required Qualifications:

• Ph.D. in Bioinformatics, Computational Biology, Data Science, Artificial Intelligence, or a related field with applications in healthcare and metabolomics.
• Strong experience in machine learning, deep learning, and AI frameworks (TensorFlow, PyTorch, Scikit-learn).
• Knowledge of metabolomics data analysis, including LC-MS, NMR data preprocessing, normalization, and feature extraction.
• Familiarity with multi-omics data integration, biomarker discovery workflows, and metabolic pathway enrichment analysis (e.g., KEGG, HMDB, Reactome).
• Experience with statistical modeling and multivariate analysis techniques (e.g., PLS-DA, PCA, random forest classifiers).
• Proficiency in programming languages such as Python, R, and experience with bioinformatics pipelines.
• A proven track record of scientific publications in metabolomics, AI, or computational biology journals.
• Excellent communication and teamwork skills, with the ability to collaborate in multidisciplinary and clinical research settings.

Application Process:

Interested candidates should submit the following documents as a single PDF:

1. A cover letter describing research interests, motivation, and relevant experience.
2. A detailed Curriculum Vitae (CV) including a list of publications.
3. Contact details for two academic referees.